Aperag

v1.0.0Knowledge & Memorystable

🐍 ☁️ 🏠 - Production-ready RAG platform combining Graph RAG, vector search, and full-text search. Best choice for building your own Knowledge Graph and for Context Engineering

agentscontext-engineeringgraphragknowledge-graphmcp
Share:
1,170
Stars
0
Downloads
0
Weekly
0/5

What is Aperag?

Aperag is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🐍 ☁️ 🏠 - production-ready rag platform combining graph rag, vector search, and full-text search. best choice for building your own knowledge graph and for context engineering

🐍 ☁️ 🏠 - Production-ready RAG platform combining Graph RAG, vector search, and full-text search. Best choice for building your own Knowledge Graph and for Context Engineering

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 🐍 ☁️ 🏠 - Production-ready RAG platform combining Graph RAG,

Use Cases

Build custom knowledge graphs combining Graph RAG and vector search.
Enable full-text search on large document collections.
Enhance context engineering for AI applications.
apecloud

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx aperag

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Aperag

ApeRAG is a production-ready Retrieval-Augmented Generation platform that combines Graph RAG, vector search, and full-text search into a single self-hosted service, exposing its knowledge-retrieval capabilities through a built-in MCP server. It lets AI assistants browse document collections, perform hybrid searches across large corpora, and answer natural-language questions grounded in your own documents. Teams use ApeRAG to build custom knowledge graphs over internal documentation, codebases, or research papers, making it a strong foundation for context engineering in enterprise AI workflows.

Prerequisites

  • Docker and Docker Compose installed (minimum 2 CPU cores, 4 GB RAM)
  • An ApeRAG API key generated from the web interface after deployment
  • An MCP-capable client such as Claude Desktop or any MCP-compatible AI assistant
  • Git installed to clone the repository
1

Clone the repository and copy the environment template

Clone the ApeRAG repository and create your .env file from the provided template. Review the template to configure any LLM provider keys or storage settings before starting the stack.

git clone https://github.com/apecloud/ApeRAG.git
cd ApeRAG
cp envs/env.template .env
2

Start the ApeRAG stack with Docker Compose

Launch all services using Docker Compose. The stack pulls the latest images automatically. Use the optional docray profile if you need enhanced document parsing with OCR capabilities.

# Standard startup
docker-compose up -d --pull always

# With enhanced document parsing (optional)
DOCRAY_HOST=http://aperag-docray:8639 docker compose --profile docray up -d
3

Open the web interface and create a collection

Navigate to http://localhost:3000/web/ to access the ApeRAG dashboard. Create a knowledge collection, upload your documents, and wait for the indexing pipeline to complete. Then generate an API key from the settings page.

4

Configure your MCP client to connect to ApeRAG

Add the ApeRAG MCP server to your client configuration. The server runs at http://localhost:8000/mcp/ and requires your API key as a Bearer token in the Authorization header.

{
  "mcpServers": {
    "aperag-mcp": {
      "url": "http://localhost:8000/mcp/",
      "headers": {
        "Authorization": "Bearer your-api-key-here"
      }
    }
  }
}
5

Verify the connection and explore your knowledge base

Ask your AI assistant to list available collections or perform a search. The MCP server exposes three primary tools: collection browsing, hybrid search (vector + full-text + graph), and natural language question answering over documents.

Aperag Examples

Client configuration

MCP client config for connecting Claude Desktop to a locally running ApeRAG instance.

{
  "mcpServers": {
    "aperag-mcp": {
      "url": "http://localhost:8000/mcp/",
      "headers": {
        "Authorization": "Bearer your-aperag-api-key"
      }
    }
  }
}

Prompts to try

Example prompts that exercise ApeRAG's collection browsing, hybrid search, and document Q&A capabilities.

- "List all available knowledge collections in ApeRAG"
- "Search the documentation collection for information about authentication middleware"
- "What does the onboarding guide say about setting up a new developer environment?"
- "Find all documents related to database schema migrations using hybrid search"
- "Ask the knowledge base: what are the main differences between our v1 and v2 API?"

Troubleshooting Aperag

MCP connection fails with 401 Unauthorized

Ensure your API key is correct and included as 'Authorization: Bearer <key>' in the headers. API keys are generated per-user in the ApeRAG web interface. You can also set APERAG_API_KEY as an environment variable if the client supports it.

Docker Compose fails to start due to insufficient resources

ApeRAG requires at least 2 CPU cores and 4 GB RAM. Check Docker Desktop resource settings and increase memory allocation. On Linux, verify that Docker has sufficient system resources with 'docker info'.

Documents are uploaded but search returns no results

Indexing takes time after upload, especially for large documents or when using the Graph RAG pipeline. Check the ApeRAG dashboard at http://localhost:3000/web/ for indexing status. The API documentation at http://localhost:8000/docs shows indexing job endpoints.

Frequently Asked Questions about Aperag

What is Aperag?

Aperag is a Model Context Protocol (MCP) server that 🐍 ☁️ 🏠 - production-ready rag platform combining graph rag, vector search, and full-text search. best choice for building your own knowledge graph and for context engineering It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Aperag?

Follow the installation instructions on the Aperag GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Aperag?

Aperag works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Aperag free to use?

Yes, Aperag is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "aperag": { "command": "npx", "args": ["-y", "aperag"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Aperag?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides